FMMI: Flow Matching Mutual Information Estimation
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866914315250958336 |
|---|---|
| author | Butakov, Ivan Semenenko, Alexander Kirova, Valeriya Frolov, Alexey Oseledets, Ivan |
| author_facet | Butakov, Ivan Semenenko, Alexander Kirova, Valeriya Frolov, Alexey Oseledets, Ivan |
| contents | We introduce a novel Mutual Information (MI) estimator that fundamentally reframes the discriminative approach. Instead of training a classifier to discriminate between joint and marginal distributions, we learn a normalizing flow that transforms one into the other. This technique produces a computationally efficient and precise MI estimate that scales well to high dimensions and across a wide range of ground-truth MI values. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_08552 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | FMMI: Flow Matching Mutual Information Estimation Butakov, Ivan Semenenko, Alexander Kirova, Valeriya Frolov, Alexey Oseledets, Ivan Machine Learning Information Theory 94A16 (Primary) 68T07, 94A17 (Secondary) E.4; H.1.1 We introduce a novel Mutual Information (MI) estimator that fundamentally reframes the discriminative approach. Instead of training a classifier to discriminate between joint and marginal distributions, we learn a normalizing flow that transforms one into the other. This technique produces a computationally efficient and precise MI estimate that scales well to high dimensions and across a wide range of ground-truth MI values. |
| title | FMMI: Flow Matching Mutual Information Estimation |
| topic | Machine Learning Information Theory 94A16 (Primary) 68T07, 94A17 (Secondary) E.4; H.1.1 |
| url | https://arxiv.org/abs/2511.08552 |